Olivia Schaefer

OliviaSchaefer.json

https://arbital.com/p/OliviaSchaefer

by Olivia Schaefer Oct 13 2015

Index
Olivia Schaefer

Automatically generated page for "Olivia Schaefer" user. Click here to edit.

Created

wiki

Active learning for opaque, powerful predictors #### (An open theoretical question relevant to AI control.) Suppose that I have a very powerful p…
Children in a sidebar I always forget to scroll all the way down. I shouldn't have to. Putting children in a sidebar allow…
Collusion is a major concern Breaking out of the Prisoner's Dilemma
Human in the counterfactual loop Consider an autonomous system which is buying or selling assets, operating heavy machinery, or makin…
Learning representations Many AI systems form internal representations of their current environment or of particular data. Pr…
Reinforcement learning Reinforcement learning is the process by which an agent learns what actions to take by maximizing a …
Reward engineering This post gestures at a handful of research questions with a loose thematic connection. ## The idea…
Taking people seriously

group

Olivia Schaefer

comment

I think Wikipedia does it pretty well. Defaulting to capitalizing with the option to disable it look…

Edited

Approval-based agents An alternative to goal-directed behavior - Paul Christiano
Consequentialist cognition The cognitive ability to foresee the consequences of actions, prefer some outcomes to others, and output actions leading to the preferred outcomes. - Eliezer Yudkowsky
Omnipotence test for AI safety Would your AI produce disastrous outcomes if it suddenly gained omnipotence and omniscience? If so, why did you program something that *wants* to hurt you and is held back only by lacking the power? - Eliezer Yudkowsky
Scalable AI Control By AI control, I mean the problem of getting AI systems to do what we want them to do, to the best o… - Paul Christiano